@misc{agentharm,
  title = {AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents},
  url = {https://arxiv.org/abs/2410.09024v3},
  author = {Maksym Andriushchenko and Alexandra Souly and Mateusz Dziemian and Derek Duenas and Maxwell Lin and Justin Wang and Dan Hendrycks and Andy Zou and Zico Kolter and Matt Fredrikson and Eric Winsor and Jerome Wynne and Yarin Gal and Xander Davies},
  year = {2024},
  date = {2024-10-11},
  version = {arXiv:2410.09024v3},
  note = {arXiv:2410.09024v3}
}

@misc{agentharm-nuwa,
  title = {AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/agentharm/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--agentharm.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--agentharm.json.}
}